Fangzhou Hong

papers

1,747

total citations

papers (20)

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

NEURIPS 2025arXiv

citations

MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

CVPR 2025arXiv

citations

DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification

ICCV 2023

citations

Fangzhou Hong

papers (20)

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

LiDAR-Based Panoptic Segmentation via Dynamic Shifting Network

SHERF: Generalizable Human NeRF from a Single Image

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

CityDreamer: Compositional Generative Model of Unbounded 3D Cities

Large Motion Model for Unified Multi-Modal Motion Generation

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation

Generative Gaussian Splatting for Unbounded 3D City Generation

EgoLife: Towards Egocentric Life Assistant

Garment4D: Garment Reconstruction from Point Cloud Sequences

Versatile Multi-Modal Pre-Training for Human-Centric Perception

4D Panoptic Scene Graph Generation

EgoLM: Multi-Modal Language Model of Egocentric Motions

SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification

papers (20)

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling

LiDAR-Based Panoptic Segmentation via Dynamic Shifting Network

SHERF: Generalizable Human NeRF from a Single Image

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

CityDreamer: Compositional Generative Model of Unbounded 3D Cities

Large Motion Model for Unified Multi-Modal Motion Generation

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation

Generative Gaussian Splatting for Unbounded 3D City Generation

EgoLife: Towards Egocentric Life Assistant

Garment4D: Garment Reconstruction from Point Cloud Sequences

Versatile Multi-Modal Pre-Training for Human-Centric Perception

4D Panoptic Scene Graph Generation

EgoLM: Multi-Modal Language Model of Egocentric Motions

SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification